metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-img_orientation
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7280604310153299
swin-tiny-patch4-window7-224-img_orientation
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4743
- Accuracy: 0.7281
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6659 | 1.0 | 316 | 0.5536 | 0.6850 |
| 0.5971 | 2.0 | 633 | 0.4986 | 0.7170 |
| 0.5782 | 3.0 | 949 | 0.4825 | 0.7172 |
| 0.5428 | 4.0 | 1266 | 0.4664 | 0.7141 |
| 0.5131 | 5.0 | 1582 | 0.4785 | 0.7150 |
| 0.4851 | 6.0 | 1899 | 0.4706 | 0.7225 |
| 0.4457 | 7.0 | 2215 | 0.4729 | 0.7187 |
| 0.4407 | 8.0 | 2532 | 0.4759 | 0.7207 |
| 0.4636 | 9.0 | 2848 | 0.4732 | 0.7250 |
| 0.4212 | 9.98 | 3160 | 0.4743 | 0.7281 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3